Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy

Kondo, Kazuma; Hasegawa, Tatsuhito

doi:10.3390/s21227743

Cited by 5 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) level 1 OEP: Directly classifying the OEP sub-classes was difficult for the machine learning models, due to the relatively small number of training examples and large number of classes. Therefore, the OEP sub-classes were merged according to the characteristics of the exercises, in order to build a hierarchical system, as proposed in [24]. This technique reduced the number of classes while maintaining the same number of training examples.…”

Section: B Oep Exercises Annotationmentioning

confidence: 99%

Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models

Shang,

Dedeyne,

Dupont

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Otago Exercise Program (OEP) is a rehabilitation program for older adults to improve frailty, sarcopenia, and balance. Accurate monitoring of patient involvement in OEP is challenging, as self-reports (diaries) are often unreliable. The development of wearable sensors and their use in Human Activity Recognition (HAR) systems has lead to a revolution in healthcare. However, the use of such HAR systems for OEP still shows limited performance. The objective of this study is to build an unobtrusive and accurate system to monitor OEP for older adults. Data was collected from 18 older adults wearing a single waist-mounted Inertial Measurement Unit (IMU). Two datasets were recorded, one in a laboratory setting, and one at the homes of the patients. A hierarchical system is proposed with two stages: 1) using a deep learning model to recognize whether the patients are performing OEP or activities of daily life (ADLs) using a 10-minute sliding window; 2) based on stage 1, using a 6second sliding window to recognize the OEP sub-classes. Results showed that in stage 1, OEP could be recognized with window-wise f1-scores over 0.95 and Intersectionover-Union (IoU) f1-scores over 0.85 for both datasets. In stage 2, for the home scenario, four activities could be recognized with f1-scores over 0.8: ankle plantarflexors, abdominal muscles, knee bends, and sit-to-stand. These results showed the potential of monitoring the compliance of OEP using a single IMU in daily life. Also, some OEP subclasses are possible to be recognized for further analysis.

show abstract

Section: B Oep Exercises Annotationmentioning

confidence: 99%

Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models

Shang,

Dedeyne,

Dupont

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…Other methods include a CELearning model using multiple layers of four different classifiers [ 23 ], an ensemble learning model using Adaboost and SVM [ 24 ], a model combining gated recurrent units (GRU), CNN, and deep neural networks (DNN) [ 25 ], and ensemble learning with multiple deep learning models [ 26 ]. Another study [ 27 ] applied multiple data augmentation to input data to perform activity recognition using ensemble learning but did not focus on frequency characteristics.…”

Section: Related Researchmentioning

confidence: 99%

Sensor-Based Activity Recognition Using Frequency Band Enhancement Filters and Model Ensembles

Tsutsumi

Kondo

Takenaka

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Deep learning methods are widely used in sensor-based activity recognition, contributing to improved recognition accuracy. Accelerometer and gyroscope data are mainly used as input to the models. Accelerometer data are sometimes converted to a frequency spectrum. However, data augmentation based on frequency characteristics has not been thoroughly investigated. This study proposes an activity recognition method that uses ensemble learning and filters that emphasize the frequency that is important for recognizing a certain activity. To realize the proposed method, we experimentally identified the important frequency of various activities by masking some frequency bands in the accelerometer data and comparing the accuracy using the masked data. To demonstrate the effectiveness of the proposed method, we compared its accuracy with and without enhancement filters during training and testing and with and without ensemble learning. The results showed that applying a frequency band enhancement filter during training and testing and ensemble learning achieved the highest recognition accuracy. In order to demonstrate the robustness of the proposed method, we used four different datasets and compared the recognition accuracy between a single model and a model using ensemble learning. As a result, in three of the four datasets, the proposed method showed the highest recognition accuracy, indicating the robustness of the proposed method.

show abstract

“…Feichtenhofer et al [ 6 ] proposed spatial fusion and temporal fusion methods to improve HAR accuracy, achieving 93.5% and 69.2% in UCF101 and HMDB51, respectively. However, since video sequences encompass both spatial and temporal features, while a single CNN model may lose temporal features, some researchers [ 7 , 8 , 9 ] have proposed model combination methods to enhance the accuracy of HAR. For example, Zhang et al [ 10 ] combined two CNNs to form a 2D-CNN network to obtain the spatial and temporal features of video sequences, achieving an accuracy of 90.9% on the NTU-RGB+D dataset.…”

Section: Related Workmentioning

confidence: 99%

“…Finally, we derive Equation ( 6) to get Equation (7). The process of mapping spatial information from the camera to the world coordinate system is illustrated in Figure 6.…”

Section: Spatial Calibrationmentioning

confidence: 99%

Multi-Sensor Data Fusion and CNN-LSTM Model for Human Activity Recognition System

Zhou

Zhao

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

Human activity recognition (HAR) is becoming increasingly important, especially with the growing number of elderly people living at home. However, most sensors, such as cameras, do not perform well in low-light environments. To address this issue, we designed a HAR system that combines a camera and a millimeter wave radar, taking advantage of each sensor and a fusion algorithm to distinguish between confusing human activities and to improve accuracy in low-light settings. To extract the spatial and temporal features contained in the multisensor fusion data, we designed an improved CNN-LSTM model. In addition, three data fusion algorithms were studied and investigated. Compared to camera data in low-light environments, the fusion data significantly improved the HAR accuracy by at least 26.68%, 19.87%, and 21.92% under the data level fusion algorithm, feature level fusion algorithm, and decision level fusion algorithm, respectively. Moreover, the data level fusion algorithm also resulted in a reduction of the best misclassification rate to 2%~6%. These findings suggest that the proposed system has the potential to enhance the accuracy of HAR in low-light environments and to decrease human activity misclassification rates.

show abstract

Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy

Cited by 5 publications

References 45 publications

Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models

Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models

Sensor-Based Activity Recognition Using Frequency Band Enhancement Filters and Model Ensembles

Multi-Sensor Data Fusion and CNN-LSTM Model for Human Activity Recognition System

Contact Info

Product

Resources

About